This Hugging Face model provides automatic speech recognition for Polish audio using a fine-tuned wav2vec2 architecture. Developers and researchers can run it locally with Transformers and PyTorch or integrate it into speech transcription workflows.
Wav2vec2 Large Xlsr 53 Polish sits in PulseGate's Speech to text category. It focuses on transcribing Polish speech into text without building an automatic speech recognition model from scratch. Wav2vec2 Large Xlsr 53 Polish is an open-source project aimed at machine learning developers and speech researchers. Wav2vec2 Large Xlsr 53 Polish is open source under the MIT license. It runs on the web, the command line, and API, and it can be self-hosted.
Jonatas Grosman builds and maintains Wav2vec2 Large Xlsr 53 Polish, and it first shipped in 2021. Development happens publicly on GitHub with 206 stars. PulseGate's similarity index places it among 14 comparable projects. Among its 7 catalogued features are speech transcription, polish language support, and transformers integration.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do